English
Related papers

Related papers: Supply-Chain Poisoning Attacks Against LLM Coding …

200 papers

Instruction-tuned Large Language Models designed for coding tasks are increasingly employed as AI coding assistants. However, the cybersecurity vulnerabilities and implications arising from the widespread integration of these models are not…

Cryptography and Security · Computer Science 2025-03-10 Md Imran Hossen , Sai Venkatesh Chilukoti , Liqun Shan , Sheng Chen , Yinzhi Cao , Xiali Hei

Large language models (LLMs) increasingly rely on retrieving information from external corpora. This creates a new attack surface: indirect prompt injection (IPI), where hidden instructions are planted in the corpora and hijack model…

Cryptography and Security · Computer Science 2026-01-13 Hongyan Chang , Ergute Bao , Xinjian Luo , Ting Yu

This position paper argues that securing LLM agents requires first defining an end-to-end correctness property that specifies when an agent's execution faithfully reflects the user's intent. Modern LLM agents operate over an…

Cryptography and Security · Computer Science 2026-05-19 Wenjie Qu , Ming Xu , Peiran Wang , Shengfang Zhai , Jiaheng Zhang , Dawn Song

Large language models (LLMs) have shown promise for automated patching, but their effectiveness depends strongly on how they are integrated into patching systems. While prior work explores prompting strategies and individual agent designs,…

Cryptography and Security · Computer Science 2026-03-03 Qingxiao Xu , Ze Sheng , Zhicheng Chen , Jeff Huang

Self-evolving LLM agents update their internal state across sessions, often by writing and reusing long-term memory. This design improves performance on long-horizon tasks but creates a security risk: untrusted external content observed…

Cryptography and Security · Computer Science 2026-03-06 Xianglin Yang , Yufei He , Shuo Ji , Bryan Hooi , Jin Song Dong

Customer-service LLM agents increasingly make policy-bound decisions (refunds, rebooking, billing disputes), but the same ``helpful'' interaction style can be exploited: a small fraction of users can induce unauthorized concessions,…

Cryptography and Security · Computer Science 2026-01-01 Jingyu Zhang

LLM agents with tool access can discover and exploit security vulnerabilities. This is known. What is not known is which features of a system prompt trigger this behaviour, and which do not. We present a systematic taxonomy based on…

Cryptography and Security · Computer Science 2026-04-07 Charafeddine Mouzouni

We witness an increasing usage of AI-assistants even for routine (classroom) programming tasks. However, the code generated on basis of a so called "prompt" by the programmer does not always meet accepted security standards. On the one…

Software Engineering · Computer Science 2024-08-15 Stefan Goetz , Andreas Schaad

LLM-powered coding agents increasingly participate in software development workflows by generating code, selecting dependencies, and producing package installation commands. This creates a new software supply chain risk: when an agent…

Cryptography and Security · Computer Science 2026-05-29 Chia-Yi Hsu , Chia-Mu Yu , Chun-Ying Huang , Jun Sakuma

Large Language Models (LLMs) remain vulnerable to jailbreak attacks that bypass their safety mechanisms. Existing attack methods are fixed or specifically tailored for certain models and cannot flexibly adjust attack strength, which is…

Cryptography and Security · Computer Science 2024-10-08 Yiting Dong , Guobin Shen , Dongcheng Zhao , Xiang He , Yi Zeng

By providing a standardized interface for LLM agents to interact with external tools, the Model Context Protocol (MCP) is quickly becoming a cornerstone of the modern autonomous agent ecosystem. However, it creates novel attack surfaces due…

Cryptography and Security · Computer Science 2025-08-22 Zhiqiang Wang , Yichao Gao , Yanting Wang , Suyuan Liu , Haifeng Sun , Haoran Cheng , Guanquan Shi , Haohua Du , Xiangyang Li

Deep learning (DL) compilers are core infrastructure in modern DL systems, offering flexibility and scalability beyond vendor-specific libraries. This work uncovers a fundamental vulnerability in their design: can an official, unmodified…

Cryptography and Security · Computer Science 2025-10-28 Simin Chen , Jinjun Peng , Yixin He , Junfeng Yang , Baishakhi Ray

Recent advancements in large language models (LLMs) have revolutionized code intelligence by improving programming productivity and alleviating challenges faced by software developers. To further improve the performance of LLMs on specific…

Cryptography and Security · Computer Science 2024-10-07 Yifei Ge , Weisong Sun , Yihang Lou , Chunrong Fang , Yiran Zhang , Yiming Li , Xiaofang Zhang , Yang Liu , Zhihong Zhao , Zhenyu Chen

AI agent-based systems are becoming increasingly integral to modern software architectures, enabling autonomous decision-making, dynamic task execution, and multimodal interactions through large language models (LLMs). However, these…

Insider threats pose a persistent and critical security risk, yet are notoriously difficult to detect in complex enterprise environments, where malicious actions are often hidden within seemingly benign user behaviors. Although…

Cryptography and Security · Computer Science 2026-01-06 Jiongchi Yu , Xiaofei Xie , Qiang Hu , Yuhan Ma , Ziming Zhao

Large Language Models (LLMs) are widely deployed in applications that accept user-submitted content, such as uploaded documents or pasted text, for tasks like summarization and question answering. In this paper, we identify a new class of…

Cryptography and Security · Computer Science 2025-08-28 Zhuotao Lian , Weiyu Wang , Qingkui Zeng , Toru Nakanishi , Teruaki Kitasuka , Chunhua Su

The integration of external data services (e.g., Model Context Protocol, MCP) has made large language model-based agents increasingly powerful for complex task execution. However, this advancement introduces critical security…

Cryptography and Security · Computer Science 2026-02-25 Che Wang , Jiaming Zhang , Ziqi Zhang , Zijie Wang , Yinghui Wang , Jianbo Gao , Tao Wei , Zhong Chen , Wei Yang Bryan Lim

According to constructivist theory, students learn software security more effectively when examples are grounded in their own code. Generic examples often fail to connect with students' prior work, limiting engagement and understanding.…

Cryptography and Security · Computer Science 2026-04-16 Matthew Frazier , Kostadin Damevski

Protecting software supply chains from malicious packages is paramount in the evolving landscape of software development. Attacks on the software supply chain involve attackers injecting harmful software into commonly used packages or…

Cryptography and Security · Computer Science 2024-02-13 S. Halder , M. Bewong , A. Mahboubi , Y. Jiang , R. Islam , Z. Islam , R. Ip , E. Ahmed , G. Ramachandran , A. Babar

Agent skills introduce a new and more severe form of indirect injection for LLM agents: unlike traditional indirect prompt injection, attackers can hide malicious instructions inside a dense, action-oriented skill that already functions as…

Cryptography and Security · Computer Science 2026-04-28 Wenjie Xiao , Xuehai Tang , Biyu Zhou , Songlin Hu , Jizhong Han